Perbandingan hasil prediksi metode random forest dan support vector regression dalam memprediksi harga emas = Comparison of prediction results between random forest and support vector regression methods in predicting gold prices

Halim, Celine Pricellia (2024) Perbandingan hasil prediksi metode random forest dan support vector regression dalam memprediksi harga emas = Comparison of prediction results between random forest and support vector regression methods in predicting gold prices. Bachelor thesis, Universitas Pelita Harapan.

	Text (Title) Title.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (250kB)
	Text (Abstract) Abstract.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (727kB)
	Text (ToC) ToC.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (806kB)
	Text (Chapter1) Chapter1.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (760kB)
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (948kB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (703kB)
	Text (Bibliography) Bibliography.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (704kB)
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (3MB)

Abstract

Emas merupakan salah satu komoditas yang memiliki peran penting sebagai salah satu aset investasi yang diminati. Memahami fluktuasi harga emas menjadi krusial bagi investor dalam mengambil keputusan investasi. Oleh karena itu, penelitian ini bertujuan untuk mengevaluasi dan membandingkan kinerja dua metode prediksi, yaitu Random Forest dan Support Vector Regression (SVR), dalam memprediksi harga spot emas AS. Data historis harga emas dan enam indikator pasar AS digunakan dalam rentang waktu dari 1 Januari 2013 hingga 31 Desember 2023. Metrik evaluasi yang digunakan meliputi R-squared, Mean Absolute Error (MAE), dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa Random Forest memiliki kinerja lebih baik daripada SVR pada sebagian besar periode. Namun, setelah dilakukan optimisasi parameter pada SVR, model SVR dengan kernel RBF mampu mengungguli Random Forest dalam semua periode. Temuan ini menyoroti pentingnya penggunaan teknik prediksi yang tepat dalam mengatasi kompleksitas fluktuasi harga emas, memberikan wawasan yang berharga bagi para investor. / In the realm of global financial markets, gold plays a crucial role as one of the sought-after investment assets. Understanding the fluctuations in gold prices is paramount for investors in making investment decisions. Therefore, this research aims to evaluate and compare the performance of two prediction methods, namely Random Forest and Support Vector Regression (SVR), in forecasting the spot price of gold in the United States. Historical gold price data and six indicators from the US market are utilized spanning from January 1, 2013, to December 30, 2022. Evaluation metrics employed include R-squared, Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). The findings reveal that Random Forest outperforms SVR in most periods. However, after parameter optimization, SVR with the RBF kernel surpasses Random Forest in all periods. This underscores the importance of employing the appropriate prediction techniques in addressing the complexities of gold price fluctuations, providing valuable insights for investors.

Actions (login required)

View Item